End of training

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2041
-- F1: 0.7312
-- Exact Match: 0.59
+- Loss: 1.1988
+- F1: 0.7649
+- Exact Match: 0.634
 
 ## Model description
 
@@ -38,10 +38,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 3.7185140364032e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3
@@ -50,14 +52,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     | Exact Match |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:-----------:|
-| 2.582         | 1.0   | 250  | 1.4052          | 0.6466 | 0.511       |
-| 1.2757        | 2.0   | 500  | 1.2138          | 0.7143 | 0.573       |
-| 1.0031        | 3.0   | 750  | 1.2041          | 0.7312 | 0.59        |
+| 0.8014        | 1.0   | 125  | 1.3209          | 0.7185 | 0.579       |
+| 0.9114        | 2.0   | 250  | 1.1532          | 0.7515 | 0.623       |
+| 0.6644        | 3.0   | 375  | 1.1988          | 0.7649 | 0.634       |
 
 
 ### Framework versions
 
-- Transformers 4.36.2
-- Pytorch 2.1.0+cu121
-- Datasets 2.16.1
-- Tokenizers 0.15.0
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -67,7 +67,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.36.2",
+  "transformers_version": "4.41.2",
   "use_cache": true,
   "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51a34cb8db7ffc240aaf3f634d9d857a0042fc4371f33e760bd3078ca42c34e3
+oid sha256:b4c098311fe8fc9d3cef762b24e6320f838731059a5d19b7b686e02fbaec3ddf
 size 557717800

runs/Jun24_07-47-52_9b938ea75028/events.out.tfevents.1719215272.9b938ea75028.1492.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb87231fddac7275bb8d74772129fd1b1dcbc71e393251dc9bfa22a3e6cf9c3
+size 6074

runs/Jun24_07-49-57_9b938ea75028/events.out.tfevents.1719215397.9b938ea75028.1492.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5a73ed811400493c4eb51c95c7f0f9ba820a6e2051395bdb8e75e0e8f89a165
+size 7959

tokenizer.json

@@ -97,6 +97,7 @@
     "end_of_word_suffix": "",
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "<s>": 0,
       "<pad>": 1,

tokenizer_config.json

@@ -48,7 +48,7 @@
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",
-  "model_max_length": 1024,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "tokenizer_class": "BartTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21f560049ce8ec58e69b5850ec29fa79f2ee2743c69b55c9b21e22055075e404
-size 4664
+oid sha256:384836a68ffb46b3b59e7a350ccfa7ecab30aef4e43f8b4ad82d8724ba1f6919
+size 5112